Skip to content
Snippets Groups Projects
Commit 95d45227 authored by Peter van 't Hof's avatar Peter van 't Hof
Browse files

Move breaking classes

parent 6300d051
No related branches found
No related tags found
No related merge requests found
Hide whitespace changes
Inline Side-by-side
Showing
with 0 additions and 424 deletions
public/yamsvp/src/main/scala/nl/lumc/sasc/biopet/extensions/pindel/Pindel.scala deleted 100644 → 0
+ 0
− 86
View file @ 6300d051
/**
* Biopet is built on top of GATK Queue for building bioinformatic
* pipelines. It is mainly intended to support LUMC SHARK cluster which is running
* SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
* should also be able to execute Biopet tools and pipelines.
*
* Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
*
* Contact us at: sasc@lumc.nl
*
* A dual licensing mode is applied. The source code within this project that are
* not part of GATK Queue is freely available for non-commercial use under an AGPL
* license; For commercial users or users who do not want to follow the AGPL
* license, please contact us to obtain a separate license.
*/
package nl.lumc.sasc.biopet.extensions.pindel
import java.io.File
import nl.lumc.sasc.biopet.core.{ BiopetQScript, PipelineCommand }
import nl.lumc.sasc.biopet.utils.config.Configurable
import org.broadinstitute.gatk.queue.QScript
/// Pindel is actually a mini pipeline executing binaries from the pindel package
class Pindel(val root: Configurable) extends QScript with BiopetQScript {
def this() = this(null)
@Input(doc = "Input file (bam)")
var input: File = _
@Input(doc = "Reference Fasta file")
var reference: File = _
@Argument(doc = "Work directory")
var workdir: String = _
// @Output(doc = "Pindel VCF output")
// lazy val outputvcf: File = {
// new File(workdir + "/" + input.getName.substring(0, input.getName.lastIndexOf(".bam")) + ".pindel.vcf")
// }
@Output(doc = "Pindel config")
lazy val configfile: File = {
new File(workdir + "/" + input.getName.substring(0, input.getName.lastIndexOf(".bam")) + ".pindel.cfg")
}
@Output(doc = "Pindel raw output")
lazy val outputvcf: File = {
new File(workdir + "/" + input.getName.substring(0, input.getName.lastIndexOf(".bam")) + ".pindel.vcf")
}
override def init() {
}
def biopetScript() {
// read config and set all parameters for the pipeline
logger.info("Starting Pindel configuration")
val cfg = PindelConfig(this, input, this.configfile)
outputFiles += ("pindel_cfg" -> cfg.output)
add(cfg)
val output: File = this.outputvcf
val pindel = PindelCaller(this, cfg.output, output)
add(pindel)
outputFiles += ("pindel_tsv" -> pindel.output)
// val output_vcf: File = this.outputvcf
// convert this tsv to vcf using the python script
}
// private def swapExtension(inputFile: String) = inputFile.substring(0, inputFile.lastIndexOf(".bam")) + ".pindel.tsv"
}
object Pindel extends PipelineCommand {
def apply(root: Configurable, input: File, reference: File, runDir: String): Pindel = {
val pindel = new Pindel(root)
pindel.input = input
pindel.reference = reference
pindel.workdir = runDir
// run the following for activating the pipeline steps
pindel.init()
pindel.biopetScript()
pindel
}
}
\ No newline at end of file
public/yamsvp/src/main/scala/nl/lumc/sasc/biopet/extensions/pindel/PindelCaller.scala deleted 100644 → 0
+ 0
− 72
View file @ 6300d051
/**
* Biopet is built on top of GATK Queue for building bioinformatic
* pipelines. It is mainly intended to support LUMC SHARK cluster which is running
* SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
* should also be able to execute Biopet tools and pipelines.
*
* Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
*
* Contact us at: sasc@lumc.nl
*
* A dual licensing mode is applied. The source code within this project that are
* not part of GATK Queue is freely available for non-commercial use under an AGPL
* license; For commercial users or users who do not want to follow the AGPL
* license, please contact us to obtain a separate license.
*/
package nl.lumc.sasc.biopet.extensions.pindel
import java.io.File
import nl.lumc.sasc.biopet.core.BiopetCommandLineFunction
import nl.lumc.sasc.biopet.utils.config.Configurable
import org.broadinstitute.gatk.utils.commandline.{ Argument, Input, Output }
class PindelCaller(val root: Configurable) extends BiopetCommandLineFunction {
executable = config("exe", default = "pindel", freeVar = false)
override def defaultCoreMemory = 5.0
override def defaultThreads = 8
override def versionRegex = """Pindel version:? (.*)""".r
override def versionExitcode = List(1)
override def versionCommand = executable
@Input(doc = "The pindel configuration file")
var input: File = _
@Input(doc = "Fasta reference")
var reference: File = config("reference")
// this is a pointer to where the results files will be stored
// inside this directory, we can expect files named:
// <prefix>_D
// <prefix>_SI
// <prefix>_I
// <prefix>_TR
@Argument(doc = "Work directory")
var workdir: String = _
@Output(doc = "Pindel VCF output")
var output: File = _
var window_size: Option[Int] = config("window_size", default = 5)
override def beforeCmd() {
}
def cmdLine = required(executable) +
"-i " + required(input) +
"-f " + required(reference) +
"-o " + required(output) +
optional("-w", window_size) +
optional("-T", nCoresRequest)
}
object PindelCaller {
def apply(root: Configurable, input: File, output: File): PindelCaller = {
val caller = new PindelCaller(root)
caller.input = input
caller.output = output
caller
}
}
public/yamsvp/src/main/scala/nl/lumc/sasc/biopet/extensions/pindel/PindelConfig.scala deleted 100644 → 0
+ 0
− 86
View file @ 6300d051
/**
* Biopet is built on top of GATK Queue for building bioinformatic
* pipelines. It is mainly intended to support LUMC SHARK cluster which is running
* SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
* should also be able to execute Biopet tools and pipelines.
*
* Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
*
* Contact us at: sasc@lumc.nl
*
* A dual licensing mode is applied. The source code within this project that are
* not part of GATK Queue is freely available for non-commercial use under an AGPL
* license; For commercial users or users who do not want to follow the AGPL
* license, please contact us to obtain a separate license.
*/
package nl.lumc.sasc.biopet.extensions.pindel
import java.io.File
import nl.lumc.sasc.biopet.core.{ BiopetJavaCommandLineFunction, ToolCommand }
import nl.lumc.sasc.biopet.utils.config.Configurable
import org.broadinstitute.gatk.utils.commandline.{ Argument, Input, Output }
class PindelConfig(val root: Configurable) extends BiopetJavaCommandLineFunction {
javaMainClass = getClass.getName
@Input(doc = "Bam File")
var input: File = _
@Output(doc = "Output Config file")
var output: File = _
@Argument(doc = "Insertsize")
var insertsize: Option[Int] = _
override def commandLine = super.commandLine +
"-i" + required(input) +
"-s" + required(insertsize) +
"-o" + required(output)
}
object PindelConfig extends ToolCommand {
def apply(root: Configurable, input: File, output: File): PindelConfig = {
val conf = new PindelConfig(root)
conf.input = input
conf.output = output
conf
}
def apply(root: Configurable, input: File, outputDir: String): PindelConfig = {
val dir = if (outputDir.endsWith("/")) outputDir else outputDir + "/"
val outputFile = new File(dir + swapExtension(input.getName))
apply(root, input, outputFile)
}
def apply(root: Configurable, input: File): PindelConfig = {
apply(root, input, new File(swapExtension(input.getAbsolutePath)))
}
private def swapExtension(inputFile: String) = inputFile.substring(0, inputFile.lastIndexOf(".bam")) + ".pindel.cfg"
case class Args(inputbam: File = null, samplelabel: Option[String] = None, insertsize: Option[Int] = None) extends AbstractArgs
class OptParser extends AbstractOptParser {
opt[File]('i', "inputbam") required () valueName "<bamfile/path>" action { (x, c) =>
c.copy(inputbam = x)
} text "Please specify the input bam file"
opt[String]('l', "samplelabel") valueName "<sample label>" action { (x, c) =>
c.copy(samplelabel = Some(x))
} text "Sample label is missing"
opt[Int]('s', "insertsize") valueName "<insertsize>" action { (x, c) =>
c.copy(insertsize = Some(x))
} text "Insertsize is missing"
}
/**
* @param args the command line arguments
*/
def main(args: Array[String]): Unit = {
val argsParser = new OptParser
val commandArgs: Args = argsParser.parse(args, Args()) getOrElse sys.exit(1)
val input: File = commandArgs.inputbam
}
}
public/yamsvp/src/main/scala/nl/lumc/sasc/biopet/pipelines/yamsvp/Yamsvp.scala deleted 100644 → 0
+ 0
− 155
View file @ 6300d051
/**
* Biopet is built on top of GATK Queue for building bioinformatic
* pipelines. It is mainly intended to support LUMC SHARK cluster which is running
* SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
* should also be able to execute Biopet tools and pipelines.
*
* Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
*
* Contact us at: sasc@lumc.nl
*
* A dual licensing mode is applied. The source code within this project that are
* not part of GATK Queue is freely available for non-commercial use under an AGPL
* license; For commercial users or users who do not want to follow the AGPL
* license, please contact us to obtain a separate license.
*/
/*
* Structural variation calling
*/
package nl.lumc.sasc.biopet.pipelines.yamsvp
import java.io.File
import nl.lumc.sasc.biopet.utils.config.Configurable
import nl.lumc.sasc.biopet.core.{ MultiSampleQScript, PipelineCommand }
import nl.lumc.sasc.biopet.extensions.Ln
import nl.lumc.sasc.biopet.extensions.breakdancer.Breakdancer
import nl.lumc.sasc.biopet.extensions.clever.CleverCaller
import nl.lumc.sasc.biopet.extensions.igvtools.IGVToolsCount
import nl.lumc.sasc.biopet.extensions.sambamba.{ SambambaMarkdup, SambambaMerge }
//import nl.lumc.sasc.biopet.extensions.pindel.Pindel
import nl.lumc.sasc.biopet.extensions.delly.Delly
import nl.lumc.sasc.biopet.pipelines.bammetrics.BamMetrics
import nl.lumc.sasc.biopet.pipelines.mapping.Mapping
import org.broadinstitute.gatk.queue.QScript
import org.broadinstitute.gatk.queue.engine.JobRunInfo
import org.broadinstitute.gatk.queue.function._
class Yamsvp(val root: Configurable) extends QScript with MultiSampleQScript {
qscript =>
def this() = this(null)
def summaryFile = null
def summaryFiles = Map()
def summarySettings = Map()
var reference: File = config("reference")
def makeSample(id: String) = new Sample(id)
class Sample(sampleId: String) extends AbstractSample(sampleId) {
def summaryFiles = Map()
def summaryStats = Map()
val alignmentDir: String = sampleDir + "alignment/"
val svcallingDir: String = sampleDir + "svcalls/"
def makeLibrary(id: String) = new Library(id)
class Library(libraryId: String) extends AbstractLibrary(libraryId) {
// val runDir: String = alignmentDir + "run_" + libraryId + "/"
def summaryFiles = Map()
def summaryStats = Map()
val mapping = new Mapping(qscript)
mapping.libId = Some(libraryId)
mapping.sampleId = Some(sampleId)
protected def addJobs(): Unit = {
mapping.input_R1 = config("R1")
mapping.input_R2 = config("R2")
mapping.outputDir = libDir
mapping.init()
mapping.biopetScript()
qscript.addAll(mapping.functions)
}
}
protected def addJobs(): Unit = {
val libraryBamfiles = libraries.map(_._2.mapping.finalBamFile).toList
val bamFile: File = if (libraryBamfiles.size == 1) {
val alignmentlink = Ln(qscript, libraryBamfiles.head,
alignmentDir + sampleId + ".merged.bam", relative = true)
alignmentlink.isIntermediate = true
add(alignmentlink)
alignmentlink.output
} else if (libraryBamfiles.size > 1) {
val mergeSamFiles = new SambambaMerge(qscript)
mergeSamFiles.input = libraryBamfiles
mergeSamFiles.output = sampleDir + sampleId + ".merged.bam"
mergeSamFiles.isIntermediate = true
add(mergeSamFiles)
mergeSamFiles.output
} else null
val bamMarkDup = SambambaMarkdup(qscript, bamFile)
add(bamMarkDup)
addAll(BamMetrics(qscript, bamMarkDup.output, alignmentDir + "metrics" + File.separator).functions)
// create an IGV TDF file
val tdfCount = IGVToolsCount(qscript, bamMarkDup.output, config("genome_name", default = "hg19"))
add(tdfCount)
/// bamfile will be used as input for the SV callers. First run Clever
// val cleverVCF : File = sampleDir + "/" + sampleID + ".clever.vcf"
val cleverDir = svcallingDir + sampleId + ".clever/"
val clever = CleverCaller(qscript, bamMarkDup.output, qscript.reference, svcallingDir, cleverDir)
add(clever)
val clever_vcf = Ln(qscript, clever.outputvcf, svcallingDir + sampleId + ".clever.vcf", relative = true)
add(clever_vcf)
val breakdancerDir = svcallingDir + sampleId + ".breakdancer/"
val breakdancer = Breakdancer(qscript, bamMarkDup.output, qscript.reference, breakdancerDir)
addAll(breakdancer.functions)
val bd_vcf = Ln(qscript, breakdancer.outputvcf, svcallingDir + sampleId + ".breakdancer.vcf", relative = true)
add(bd_vcf)
val dellyDir = svcallingDir + sampleId + ".delly/"
val delly = Delly(qscript, bamMarkDup.output, dellyDir)
addAll(delly.functions)
val delly_vcf = Ln(qscript, delly.outputvcf, svcallingDir + sampleId + ".delly.vcf", relative = true)
add(delly_vcf)
// for pindel we should use per library config collected into one config file
// val pindelDir = svcallingDir + sampleID + ".pindel/"
// val pindel = Pindel(qscript, analysisBam, this.reference, pindelDir)
// sampleOutput.vcf += ("pindel" -> List(pindel.outputvcf))
// addAll(pindel.functions)
//
// val pindel_vcf = Ln(qscript, pindel.outputvcf, svcallingDir + sampleID + ".pindel.vcf", relative = true)
// add(pindel_vcf)
//
}
}
def addMultiSampleJobs() = {}
def init() {
}
def biopetScript() {
logger.info("Starting YAM SV Pipeline")
addSamplesJobs()
}
override def onExecutionDone(jobs: Map[QFunction, JobRunInfo], success: Boolean) {
logger.info("YAM SV Pipeline has run .......................")
}
}
object Yamsvp extends PipelineCommand
\ No newline at end of file
public/yamsvp/src/test/resources/log4j.properties deleted 100644 → 0
+ 0
− 25
View file @ 6300d051
#
# Biopet is built on top of GATK Queue for building bioinformatic
# pipelines. It is mainly intended to support LUMC SHARK cluster which is running
# SGE. But other types of HPC that are supported by GATK Queue (such as PBS)
# should also be able to execute Biopet tools and pipelines.
#
# Copyright 2014 Sequencing Analysis Support Core - Leiden University Medical Center
#
# Contact us at: sasc@lumc.nl
#
# A dual licensing mode is applied. The source code within this project that are
# not part of GATK Queue is freely available for non-commercial use under an AGPL
# license; For commercial users or users who do not want to follow the AGPL
# license, please contact us to obtain a separate license.
#
# Set root logger level to DEBUG and its only appender to A1.
log4j.rootLogger=ERROR, A1
# A1 is set to be a ConsoleAppender.
log4j.appender.A1=org.apache.log4j.ConsoleAppender
# A1 uses PatternLayout.
log4j.appender.A1.layout=org.apache.log4j.PatternLayout
log4j.appender.A1.layout.ConversionPattern=%-5p [%d] [%C{1}] - %m%n
\ No newline at end of file
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment